Electrostatic dust collection dynamic control method based on multi-source data fusion

Abstract

The invention discloses an electrostatic dust collection dynamic control method based on multi-source data fusion, and belongs to the technical field of electrostatic dust collection. According to the technical scheme, particulate matter parameters, environment parameters and operation parameters are obtained; processing the particulate matter parameters, the environmental parameters and the operation parameters, and constructing a characteristic quantity set for representing an indoor dust load state, an environmental influence state, a device dust accumulation state and a discharge risk state based on the processed data; performing multi-source data fusion on the characteristic quantity set to obtain a fusion state quantity; performing indoor scene recognition based on the fusion state quantity, and outputting a scene recognition result; according to the fusion state quantity and the scene recognition result, the control quantity of the electrostatic dust collection device is calculated according to a preset control criterion; and outputting the control quantity to the electrostatic dust collection device to adjust the working state of the electrostatic field, and repeatedly updating the control quantity in a subsequent control period. The static dust collection dynamic control method based on multi-source data fusion has the beneficial effect that the static dust collection dynamic control method based on multi-source data fusion is provided.

Description

Technical Field

[0001] This invention belongs to the field of electrostatic dust removal technology, and specifically relates to a dynamic control method for electrostatic dust removal based on multi-source data fusion. Background Technology

[0002] Indoor air commonly contains pollutants such as suspended particulate matter (e.g., PM2.5, PM10), cooking fumes aerosols, dust generated from cleaning and human / pet activities, and volatile organic compounds (VOCs). To improve indoor air quality, air purification equipment is widely used. Among these, electrostatic precipitators, due to their high capture efficiency for fine particulate matter, low pressure drop, and continuous operation, are used in home indoor air purification, fume purification, and air circulation.

[0003] Existing electrostatic precipitators typically include: a fan module (such as a centrifugal or axial fan) for forming airflow channels and providing circulating air volume; an electrode structure (such as discharge electrodes and dust collection plates / screens) for ionizing and capturing dust-laden gas; a high-voltage power supply module for providing the high-voltage electric field required for ionization and capture; and control circuits for equipment control and protection. The high-voltage power supply module can generally output DC high voltage or pulsed high voltage, and the ionization intensity and electric field distribution can be changed by adjusting parameters such as output voltage / current, pulse frequency, duty cycle, and rise slope. Some devices also have polarity switching or bipolar operation modes to reduce dust accumulation on the plates and improve capture stability. The fan module can control the airflow by adjusting its speed, thereby affecting the airflow residence time, capture efficiency, and equipment noise and energy consumption.

[0004] In residential indoor applications, the operating status of electrostatic precipitators is significantly affected by environmental conditions. For example, temperature and humidity affect the dielectric properties of air, the initiation conditions of corona discharge, the formation of water films on the electrode surface, and the insulation level; increased humidity makes it easier to increase leakage current, micro-discharge, and even the risk of breakdown. Oil fume aerosols and VOCs can, in some cases, lead to increased pollution on the electrode surface, forming conductive films or adhesion layers, increasing the probability of leakage current and discharge events; at the same time, dust accumulation on the electrode plates can change the electric field distribution and lead to a decrease in dust removal efficiency. To ensure operational safety and reliability, existing technologies typically monitor operating parameters such as leakage current and discharge events on the high-voltage circuit or electrode structure, and trigger protection in case of abnormalities, such as reducing the high-voltage setpoint, reducing the duty cycle, reducing the rise slope, switching the operating mode, or reducing the fan speed.

[0005] However, the indoor pollution sources of the family and the environmental state have obvious variability and scene: for example, noise is more sensitive to sleep at night, oil fume and VOCs increase sharply for a short time when cooking, PM10 proportion rises and fluctuates obviously when cleaning, pet activity is intermittent dust raising, and discharge risk rises significantly in high humidity environment. The existing electrostatic dust removal device mostly uses fixed gear control or simple closed loop control (for example, adjusting high voltage and fan according to single particle concentration or simple threshold rule), which often cannot simultaneously consider dust removal efficiency, energy consumption, noise constraint and discharge risk constraint; at the same time, due to the diversity of sensing data sources and the rapid dynamic change, if the fusion of multi-source data and the scene recognition mechanism are lacking, the control strategy may not match, frequent switching, high energy consumption, noise exceeding or discharge risk rising may occur. Therefore, a kind of electrostatic dust removal control method is needed, which can face multiple scenes in the family, integrate multi-source data and dynamically adjust the closed loop, to improve the adaptability, stability and safety in the real family environment. SUMMARY

[0006] The purpose of the present application is to provide a kind of electrostatic dust removal dynamic control method based on multi-source data fusion.

[0007] The present application is realized by the following measures: a kind of electrostatic dust removal dynamic control method based on multi-source data fusion, characterized by, S1, the particle parameters of indoor air and environmental parameters are obtained, and the operating parameters of the electrostatic dust removal device are synchronously obtained; S2, the particle parameters, the environmental parameters and the operating parameters are processed, and a feature quantity set for representing indoor dust load state, environmental influence state, device dust accumulation state and discharge risk state is constructed based on the processed data; S3, the feature quantity set is fused with multi-source data, to obtain a fusion state quantity;Wherein the fusion state quantity includes particle concentration state, environmental influence factor, device state factor and discharge risk factor.

[0008] S4, based on the fusion state quantity, indoor scene recognition is carried out, and scene recognition result is output;Wherein the scene recognition result includes sleep mute scene, cooking oil fume scene, cleaning dust raising scene, pet activity dust raising scene and high humidity environment scene; S5, according to the fusion state quantity and the scene recognition result, the control quantity of electrostatic dust removal device is calculated according to the preset control criterion;Wherein the control quantity includes high voltage driving parameter and fan operating parameter, the preset control criterion is used to weigh between dust removal efficiency, energy consumption, noise constraint and discharge risk constraint, and the control quantity is matched with the scene recognition result; S6, output the control quantity to the electrostatic dust removal device to adjust the electrostatic field working state, and repeat S1 to S5 in the subsequent control cycle to update the control quantity, so as to realize dynamic closed-loop control of indoor electrostatic dust removal.

[0009] Further, the particulate matter parameters include PM2.5 and PM10; the environmental parameters include temperature, humidity, oil fume concentration, volatile organic compound (VOC) concentration, noise intensity, and wind speed; and the operation parameters include high-voltage output voltage or high-voltage output current, leakage current, and discharge event information.

[0010] Further, the particulate matter parameters and the environmental parameters are respectively subjected to time domain filtering to obtain smoothed data; the leakage current signal in the operation parameters is subjected to denoising processing to obtain a leakage current baseline component and a spike component; and a feature quantity set is constructed based on the smoothed data, the leakage current baseline component, and the spike component.

[0011] Further, the feature quantity set includes: a feature quantity for representing an indoor dust load state: PM2.5 concentration, PM10 concentration, PM2.5 concentration change rate, PM10 concentration change rate, and particulate matter concentration fluctuation intensity; a feature quantity for representing an environmental influence state: temperature, humidity, oil fume concentration, VOC concentration, wind speed, and change rate of the above environmental parameters; a feature quantity for representing a device dust accumulation state: wind speed attenuation amount, fan load change amount, and leakage current baseline drift amount; a feature quantity for representing a discharge risk state: leakage current spike amplitude, leakage current spike count, leakage current spike energy, and discharge event count. Further, the S3 includes: normalizing the feature quantity set, and generating a corresponding credibility weight based on fluctuation intensity and saturation state of each feature quantity; obtaining a fusion state quantity based on the normalized feature quantity and the credibility weight thereof, wherein the fusion state quantity is updated by the fusion state quantity at the previous moment and the feature quantity at the current moment; Further, the fusion state quantity includes: particulate concentration state: particulate load state quantity obtained from PM2.5 concentration, PM10 concentration, and change rate thereof; environmental influence factor: environmental influence state quantity obtained from temperature, humidity, oil fume concentration, VOC concentration, noise intensity, and wind speed; device state factor: device dust accumulation state quantity obtained from wind speed attenuation amount, fan load change amount, and leakage current baseline drift amount; Discharge risk factor: a discharge risk state quantity obtained from the leakage current peak amplitude, the leakage current peak count, the leakage current peak energy, and the discharge event count.

[0012] Further, the S4 comprises: constructing the particle concentration state, the environmental influence factor, the device state factor, and the discharge risk factor in the fusion state quantity into a scene discrimination input vector; obtaining the confidence of each scene based on the scene input vector; selecting in the scene candidate set based on the confidence of each scene: selecting the scene with the maximum confidence as the scene recognition result; when the maximum confidence is lower than the preset confidence threshold, outputting a mixed scene, and recording the scenes with the top two confidences in the mixed scene as concurrent scene recognition results; setting a holding time and a switching hysteresis threshold for the scene recognition result, maintaining the current scene recognition result within the holding time, and updating the scene recognition result only when the new scene confidence continuously exceeds the switching hysteresis threshold.

[0013] Further, the rule discrimination model determines the scene candidate set according to the following conditions: when the noise intensity is lower than the preset noise threshold and the wind speed is lower than the preset wind speed threshold, and the change rate of the particle concentration state is lower than the preset change rate threshold, the sleep mute scene is added to the scene candidate set; when the oil fume concentration and the VOCs concentration are both higher than the corresponding preset concentration threshold, and the particle concentration state shows an upward trend within a preset time, the cooking oil fume scene is added to the scene candidate set; when the proportion of PM10 relative to PM2.5 is higher than the preset proportion threshold, and the fluctuation intensity of the particle concentration state is higher than the preset fluctuation threshold, the cleaning dust scene is added to the scene candidate set; when the particle concentration state shows intermittent fluctuations and the PM10 proportion is higher than the preset proportion threshold, and the wind speed is in a preset low-to-medium wind speed interval, the pet activity dust scene is added to the scene candidate set; when the humidity is higher than the preset humidity threshold, and the discharge risk factor rises or the leakage current baseline drift amount corresponding to the device state factor is greater than the preset drift threshold, the high-humidity environment scene is added to the scene candidate set.

[0014] Further, the S5 comprises: construct a control objective function based on the fusion state quantity, and set a target weight and a constraint threshold value according to the scene recognition result; wherein the control objective function simultaneously contains a particle concentration reduction term for representing dust removal effect, a power consumption term for representing energy consumption, a noise penalty term for representing noise, and a risk penalty term for representing discharge risk; and constraint conditions are set that the noise intensity is not more than a preset noise upper limit, the discharge risk factor is not more than a preset risk upper limit, and the high voltage upper limit is reduced when the humidity is higher than a preset humidity threshold.

[0015] generate a candidate control quantity set within a preset control period, the candidate control quantity set including combinations of several groups of high-voltage driving parameters and fan running parameters; wherein the high-voltage driving parameters include set values of high-voltage output voltage or high-voltage output current, pulse frequency, duty cycle, rising edge slope, and polarity switching strategy, and the fan running parameters include fan speed set value.

[0016] For each group of candidate control quantities, predict the particle concentration change, power consumption, noise intensity, and discharge risk change in the next control period based on the fusion state quantity, and calculate the corresponding comprehensive generation value; wherein the comprehensive generation value is calculated by the control objective function, and a candidate control quantity that violates the constraint condition is marked as infeasible or has an additional penalty term.

[0017] Select the group with the smallest comprehensive generation value from the candidate control quantities that have not been marked as infeasible as the control quantity and output it to the electrostatic precipitator, so that the control quantity matches the scene recognition result.

[0018] When the scene recognition result is a sleep mute scene, increase the noise penalty weight and reduce the fan speed set value, while reducing the high-voltage output set value and maintaining the dust removal effect by increasing the pulse frequency and adjusting the duty cycle; when the scene recognition result is a cooking oil fume scene, increase the dust removal effect weight and increase the fan speed set value, while increasing the high-voltage output set value Further, the S6 includes: At the beginning of each control period, decompose the control quantity into high-voltage driving instructions and fan driving instructions, and output them to the high-voltage power supply module and the fan module respectively; wherein the high-voltage driving instructions are used to set the high-voltage output voltage or high-voltage output current, pulse frequency, duty cycle, rising edge slope, and polarity switching strategy, and the fan driving instructions are used to set the fan speed.

[0019] A soft start process is performed when updating the high-voltage driving instruction, the soft start process including stepwise lifting of a high-voltage output setting value within a preset time; when it is detected that a leakage current exceeds a preset leakage threshold or a discharge event represented by discharge event information occurs, a protection strategy is triggered, the protection strategy including one or more of lowering the high-voltage output setting value, lowering a duty cycle, lowering a rising edge slope, switching a polarity switching strategy, and lowering a fan rotating speed.

[0020] The updated particulate matter parameters, environmental parameters, and operating parameters are collected within the control period, and a dust removal effect evaluation quantity is calculated; the dust removal effect evaluation quantity includes a particulate matter concentration reduction rate and a unit energy consumption dust removal amount, and the candidate control quantity generation range or the control target function weight of the next control period is corrected based on the dust removal effect evaluation quantity.

[0021] The steps S1 to S5 are repeatedly performed in subsequent control periods, and the control quantity is updated based on the latest fusion state quantity and scene recognition result to achieve dynamic closed-loop control of indoor electrostatic dust removal.

[0022] When the control quantity changes by more than a preset change threshold in adjacent control periods, the control quantity is subjected to amplitude limiting or gradual change processing to suppress sudden changes in the electrostatic field working state caused by scene switching or transient fluctuations.

[0023] The technical scheme provided by the embodiment of the present application has the beneficial effects that: the state representation of multi-source data driving is more accurate: by simultaneously using particulate matter parameters, environmental parameters such as temperature and humidity, oil smoke, VOCs, noise, wind speed, and operating parameters such as high-voltage output, leakage current, and discharge event, multi-dimensional features such as dust load, environmental impact, device dust accumulation, and discharge risk are constructed and fused to obtain a fusion state quantity, so that the device can more comprehensively represent the coupling state of “pollution-environment-device”, and the misjudgment and miscontrol caused by a single sensor or a single index are reduced. Through indoor scene recognition based on the fusion state quantity, control weights and constraint strategies can be dynamically selected in different scenes such as sleep silence, cooking oil smoke, cleaning dust, pet dust, and high-humidity environment, so that the high-voltage driving parameters and the fan operating parameters are matched with the scene demand. Trade-off between efficiency, energy consumption, noise, and safety: by presetting control criteria (objective function + constraint) to evaluate and optimize candidate control quantities, the power consumption and noise can be suppressed while ensuring the reduction of particulate matter concentration, and the discharge risk is constrained, so that multi-objective comprehensive optimal or approximate optimal control is realized from the system level, and the limitations of traditional fixed gear or single target control are improved. By using leakage current baseline and peak component, discharge event count and other risk representation quantities, combined with soft start, amplitude limiting / gradient and protection load reduction strategies, the transient discharge and breakdown risk caused by humidity change, plate pollution or scene mutation can be reduced, the stability of the electrostatic field is improved, and the reliable operation time of the device is prolonged. By collecting updated parameters in each control period and calculating the dust removal effect evaluation quantity (such as concentration reduction rate, unit energy consumption dust removal amount), the candidate control range or target weight of the subsequent period is corrected, dynamic closed-loop control and performance self-optimization are realized, so that it is more suitable for long-term changes and individual differences in real home environment. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the present application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings listed below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laborious work.

[0025] Figure 1 is a flow chart of a dynamic electrostatic dust removal control method based on multi-source data fusion in the embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application will be further described in detail below with embodiments. Of course, the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

[0027] Reference Figure 1The application discloses a static dust removal dynamic control method based on multi-source data fusion. S1, particle parameters and environmental parameters of indoor air are acquired, and operation parameters of a static dust removal device are synchronously acquired; A k-th sampling period is represented by a sampling serial number k, and a sampling time is represented as Each parameter is represented as PM2.5 concentration is represented as PM10 concentration is represented as Temperature is represented as Humidity is represented as Oil fume concentration is represented as Volatile organic compounds (VOCs) concentration is represented as Noise intensity is represented as Wind speed is represented as High-voltage output voltage is represented as or high-voltage output current is represented as Leakage current is represented as Discharge event information is represented as .

[0028] The cooking oil fume scene is identified, oily particles are easy to adhere to the surface of a dust collection electrode plate / electrode, leading to efficiency attenuation and causing a leakage current baseline change.

[0029] Temperature Humidity : influences ionization efficiency, dielectric breakdown threshold, electrode plate surface water film formation and leakage. When the humidity is high, the field strength needs to be reduced / limited to rise, to inhibit discharge and ozone byproduct risk; Temperature influences sensor drift and air viscosity.

[0030] VOCs concentration represents cooking / cleaner / evaporation source together with oil fume, to assist scene identification and control weight adjustment.

[0031] Noise intensity is used for sleep mute constraint input (upper limit constraint / punishment term), to inhibit noise caused by a fan and high-voltage regulation.

[0032] Wind speed influences particle residence time in an electric field and capture probability.

[0033] High-voltage output voltage or high-voltage output current determines ionization intensity, capture field strength and energy consumption; and is also an important basis for judging whether output reaches a setting or is abnormal.

[0034] Leakage current An increase in leakage current often indicates humidity, board contamination, or decreased insulation, and is a precursor signal of discharge / breakdown risk.

[0035] Discharge event information It reflects the breach of the electric field operating boundary and can be used for safety protection and parameter adaptive correction.

[0036] S2. Process the particulate matter parameters, environmental parameters, and operating parameters, and construct a set of feature quantities based on the processed data to characterize the indoor dust load state, environmental impact state, device dust accumulation state, and discharge risk state. For any sequence of the particulate matter parameters and the environmental parameters that needs filtering:

[0037] Time-domain filtering is performed to obtain smoothed data.

[0038] but ,in This is the smoothed value after time-domain filtering. For time-domain filtering operators, This represents the original sampled value for the k-th period. The time-domain filtering includes one or more of the following: moving average filtering, median filtering, and exponentially weighted moving average filtering.

[0039] The leakage current signal in the operating parameters is denoised to obtain the baseline component and spike component of the leakage current. (Leakage current baseline component) With peak component Leakage current The result of the decomposition is: . Based on the smoothed data, the baseline component of the leakage current, and the peak component, a set of feature quantities is constructed. The set of feature quantities includes: Characteristic quantities used to characterize indoor dust load status: , , , as well as ;in This is the smoothed PM2.5 concentration. This is the smoothed PM10 concentration. The rate of change in PM2.5 concentration. The rate of change of PM10 concentration. This represents the intensity of particulate matter concentration fluctuations.

[0040] Characteristic quantities used to characterize the state of environmental impact: , , , , and the rate of change of the above environmental parameters ;in, The temperature is after smoothing. The humidity value is after smoothing. This is the smoothed oil fume concentration value. VOCs concentration value, This is the smoothed wind speed value. These represent the rates of change of the corresponding environmental parameters.

[0041] The rates of change for PM2.5 concentration, PM10 concentration, and various environmental parameters are all calculated as the ratio of the smoothed difference between adjacent sampling periods to the sampling period. Taking PM2.5 concentration as an example, the PM2.5 concentration change rate... Specifically:

[0042] In the formula, To represent the smoothed PM2.5 concentration value after the kth sampling period, This represents the smoothed PM2.5 concentration value from the previous sampling period. This indicates the time interval between adjacent sampling periods.

[0043] Similarly, taking temperature as an example, the rate of temperature change Specifically:

[0044] In the formula, To represent the smoothed temperature value after the kth sampling period, This represents the smoothed temperature value from the previous sampling period. This indicates the time interval between adjacent sampling periods.

[0045] In addition, the intensity of particulate matter concentration fluctuations for:

[0046] in, The window length (number of sample points) used to calculate the fluctuation intensity. When the k-th sampling period is taken as the "current point", the most recent The average level of smoothed PM2.5 concentration within each sampling point; For the first Smoothed PM2.5 concentration for each sampling period, The summation symbol indicates that the summation is performed by adding the summation symbol to the summation symbol. These items all add up.

[0047] Characteristic quantities for characterizing the dust accumulation state of the device: wind speed attenuation, fan load change, and leakage current baseline drift; The wind speed attenuation is When dust / obstruction causes the resistance to rise, the actual wind speed decreases, and the attenuation increases.

[0048] In the formula, is the wind speed attenuation, is the reference wind speed (take the "calibration wind speed under the same fan setting position").

[0049] The fan load change is When the resistance becomes larger, the fan current rises, and the load change can assist in judging the dust trend.

[0050] In the formula, is the fan load change, is the current sampling period smoothed fan current, is the smoothed fan current, indicates the smoothed fan current of the previous sampling period.

[0051] The leakage current baseline drift is Panel contamination / water film / insulation decline will cause the baseline to slowly rise, and the drift can be used for health assessment and risk constraint.

[0052] In the formula, is the leakage current baseline drift, is the leakage current baseline component of the current sampling period, is the leakage current baseline component of the previous sampling period.

[0053] Characteristic quantities for characterizing the discharge risk state: leakage current peak amplitude, leakage current peak count, leakage current peak energy, and discharge event count. Set the risk calculation window length to When the risk is calculated in the kth sampling period, the sampling periods corresponding to the samples in the window are , which is equivalent to index representing each sample point in the window.

[0054] The leakage current peak amplitude (is the maximum value of the absolute value of the leakage current peak component in the last sampling points) is specifically represented as:

[0055] In the formula, indicates the leakage current peak amplitude in the kth period window, indicates the maximum value in the window index i range, is the kth Periodic leakage current spike components.

[0056] Leakage current spike count (for the most recent) Within each sampling point, satisfying The number of sampling points is specifically expressed as:

[0057] In the formula, For the peak count within the k-th period window, The number of elements in the set (counting operator). The threshold for determining the peak value. This indicates that the sampling point was judged as a spike.

[0058] Leakage current spike energy (for the most recent Within each sampling point, the summation of the squares of the peak components multiplied by the sampling period. The obtained energy-type index is specifically expressed as follows:

[0059] The peak energy within the periodic window, To the window Summing of each sample, squared peak component , The sampling period is the peak component of the leakage current.

[0060] Discharge event count (in the most recent) Discharge event flag at each sampling point The accumulated value), specifically represented as:

[0061] In the formula, This represents the number of discharge events within the k-th period window.

[0062] S3. Perform multi-source data fusion on the set of features to obtain fused state quantities; wherein the fused state quantities include particle concentration state, environmental impact factor, device state factor and discharge risk factor.

[0063] S3 includes: normalizing the set of features and generating corresponding confidence weights based on the fluctuation intensity and saturation state of each feature. Specifically, the features obtained from S2 are concatenated into a feature vector: ; In the formula, This represents the eigenvector of the k-th period. Let M represent the i-th feature component, and M be the total feature dimension.

[0064] Normalization is performed on each feature, specifically as follows:

[0065] In the formula, This represents the i-th feature after normalization. This represents the statistical mean of the i-th feature. This represents the statistical standard deviation of the i-th feature. To prevent tiny constants with a denominator of zero, Greater than zero.

[0066] The fluctuation intensity is defined as follows for the i-th feature:

[0067] Let be the window variance (a measure of fluctuation intensity) of the i-th normalized feature. The window length is used to calculate the fluctuation intensity (variance), j represents the offset index within the window, and j represents the number of steps to backtrack from the current period k, where k is the index of the sampling period. For the k-th period, with the window length The window mean of the i-th normalized feature is calculated. This represents the period index corresponding to the j-th backtracking point within the window.

[0068] Define the saturation indicator (whether the sensor's upper / lower limits have been reached): , This indicates that the sensor corresponding to the i-th feature is in a saturated state; This indicates that the product is not saturated.

[0069] The credibility weight can be set as follows (the greater the fluctuation or the closer to saturation, the lower the weight; this is used to suppress the impact of unstable features on the fusion result):

[0070] In the formula, This represents the confidence weight of the i-th feature. This is the fluctuation suppression coefficient (value greater than 0). This is the saturation penalty coefficient.

[0071] The fusion state is obtained by normalizing the feature quantities and their confidence weights, and the fusion state is updated by the fusion state quantity of the previous time step and the feature quantity of the current time step.

[0072] The fusion state variable is defined as:

[0073] In the formula, a particle concentration state, an environmental impact factor, a device state factor, a discharge risk factor, T is a transpose operator.

[0074] The weighted aggregation values of the four types of features are constructed (taking the particle concentration state as an example, and the same applies to the others), and are specifically:

[0075] : weighted observation of particle type features; : a feature index set belonging to the particle load type (such as The numerator is a weighted sum, and the denominator is a weight normalization factor.

[0076] Recursive update (update of the fusion state quantity at the last time and the feature quantity at the current time) to obtain the particle concentration state: In the formula, particle state fusion gain, is the particle state at the last period.

[0077] Similarly:

[0078]

[0079]

[0080] In the formula, corresponding state fusion gain (environment, device, and discharge), corresponding type feature weighted aggregation value (environment, device, and discharge).

[0081] The fusion state quantity includes: particle concentration state: particle load state quantity obtained from PM2.5 concentration, PM10 concentration, and their change rates; environmental impact factor: environmental impact state quantity obtained from temperature, humidity, oil smoke concentration, VOCs concentration, noise intensity, and wind speed; device state factor: device dust accumulation state quantity obtained from wind speed attenuation, fan load change, and leakage current baseline drift; discharge risk factor: discharge risk state quantity obtained from leakage current peak amplitude, leakage current peak count, leakage current peak energy, and discharge event count.

[0082] ​S4, performing indoor scene recognition based on the fusion state quantity, and outputting a scene recognition result; wherein the scene recognition result comprises a sleep and silence scene, a cooking oil fume scene, a cleaning dust raising scene, a pet activity dust raising scene, and a high humidity environment scene; The S4 comprises: constructing a particle concentration state, an environmental influence factor, a device state factor, and a discharge risk factor in the fusion state quantity into a scene discrimination input vector;

[0083] wherein, is a scene discrimination input vector, wherein the parameters are consistent with the foregoing description.

[0084] Based on the scene input vector, a confidence degree of each scene is obtained, specifically: Let a scene set S = {1, 2, 3, 4, 5} correspond to: a sleep and silence scene, a cooking oil fume scene, a cleaning dust raising scene, a pet activity dust raising scene, and a high humidity environment scene, respectively; For each scene, a machine learning classification model (which can be generated by a logistic regression / MLP / tree model, etc.) calculates a scene score according to and obtains an original confidence degree by using a softmax:

[0085] wherein, is an original confidence degree of a scene s output by the classification model, and satisfies and , is an exponential function, is a scene score, , is a weight vector corresponding to the scene s, is a bias term corresponding to the scene s.

[0086] To avoid that the candidate set is difficult to calculate in natural language, a candidate indication quantity of each scene is defined , indicates that the scene s is added to the scene candidate set, indicates that it is not added, and the combined confidence degree is: .

[0087] The threshold values and interval symbols appearing in the definition rules are as follows: a noise threshold value: ; a wind speed threshold value: ; a change rate threshold value: ; an oil fume threshold value: ; a VOCs threshold value: ; and a proportion threshold value:​ ; fluctuation threshold: ; humidity threshold: ; drift threshold: ; low wind speed interval: ; proportion threshold:

[0088] when the noise intensity is lower than a preset noise threshold and the wind speed is lower than a preset wind speed threshold , and the change rate of the particle concentration state is lower than a preset change rate threshold , the sleep quiet scene is added to the scene candidate set; when the oil fume concentration and the VOCs concentration are both higher than the corresponding preset concentration thresholds and , and the particle concentration state shows an upward trend within a preset time, the cooking oil fume scene is added to the scene candidate set; when the proportion of PM10 relative to PM2.5 is higher than a preset proportion threshold , and the fluctuation intensity of the particle concentration state is higher than a preset fluctuation threshold , the cleaning dust raising scene is added to the scene candidate set; the proportion of PM10 relative to PM2.5 is: , to prevent the denominator from being a tiny constant.

[0089] when the particle concentration state shows intermittent fluctuation and the PM10 proportion is higher than a preset proportion threshold , and the wind speed is in a preset low wind speed interval , the pet activity dust raising scene is added to the scene candidate set; when the humidity is higher than a preset humidity threshold , and the discharge risk factor rises or the leakage current baseline drift amount corresponding to the device state factor is greater than a preset drift threshold , the high-humidity environment scene is added to the scene candidate set.

[0090] Based on the confidence of each scene, the scene candidate set is selected: the scene with the maximum confidence is selected as the scene recognition result; when the maximum confidence is lower than a preset confidence threshold, the output is a mixed scene, and the scenes ranked first and second in confidence in the mixed scene are recorded as concurrent scene recognition results.

[0091] then the maximum confidence and the mixed scene criterion formula are:

[0092] is the identification scene number, is the index that maximizes the target, For maximum confidence, if then output mixed scene, confidence threshold, concurrent scene takes the top two confidence .

[0093] S5, according to the fusion state quantity and the scene recognition result, according to the preset control criterion to calculate the control quantity of the electrostatic dust removal device; wherein the control quantity includes high voltage driving parameter and fan running parameter, the preset control criterion is used to balance between dust removal efficiency, energy consumption, noise constraint and discharge risk constraint, and the control quantity is matched with the scene recognition result; The S5 includes: constructing a control target function based on the fusion state quantity, and setting target weight and constraint threshold according to the scene recognition result; wherein the control target function simultaneously contains particle concentration reduction term for representing dust removal effect, power consumption term for representing energy consumption, noise penalty term for representing noise, and risk penalty term for representing discharge risk; and setting the constraint conditions that the noise intensity does not exceed the preset noise upper limit, the discharge risk factor does not exceed the preset risk upper limit, and the high voltage upper limit is reduced when the humidity is higher than the preset humidity threshold.

[0094] Define the control quantity (decision variable) vector: , In the formula, is the high voltage setting voltage, is the high voltage setting current, is the pulse frequency, is the duty cycle, is the rising slope parameter (which can be represented by the unit time increment), polarity switching strategy code (such as 0 = no switching, 1 = alternating polarity, 2 = short-time reverse bias, etc.), fan speed setting value.

[0095] Define the electrostatic high voltage power consumption prediction:

[0096] is the high voltage power consumption, is the actual high voltage output voltage, is the actual high voltage output current.

[0097] Then the fan power consumption can be used or approximated: , is the fan power consumption, fan power consumption coefficient (related to fan model calibration), is the fan speed.

[0098] Particle concentration reduction term: ; The total decrease in concentration, This is a weighting factor for the decrease in PM10 relative to the decrease in PM2.5 (used to combine the changes in the two particle sizes into a single comprehensive indicator). This represents the predicted / estimated value of PM2.5 concentration in the (k+)th control period. This represents the predicted / estimated value of PM10 concentration for the (k+1)th control period.

[0099] Noise penalty items:

[0100] The candidate noise prediction value can be mapped from the fan speed. ), The upper limit of noise, For truncation operators.

[0101] The same applies to risk penalty items:

[0102] Risk upper limit threshold Predicted risk value for candidates.

[0103] The formula for reducing the high-pressure upper limit constraint triggered by humidity is:

[0104] The upper limit of permissible high pressure under humidity conditions. The upper limit of the benchmark high voltage, Humidity derating factor, Humidity threshold.

[0105] The control objective function is then:

[0106] For the target weight, The cost of the objective function.

[0107] The candidate control quantity set includes several combinations of high-voltage drive parameters and fan operating parameters; wherein the high-voltage drive parameters include set values ​​of high-voltage output voltage or high-voltage output current, pulse frequency, duty cycle, rise edge slope, and polarity switching strategy, and the fan operating parameters include fan speed set values. A candidate control quantity set is generated within a preset control cycle, and the candidate control quantity set is represented as follows:

[0108] wherein, a set of candidate control variables, a number of candidate groups, is the mth candidate control variable vector.

[0109] For each group of candidate control variables, the particle concentration change, power consumption, noise intensity and discharge risk change in the next control period are predicted based on the fusion state variable, and the corresponding comprehensive generation value is calculated; wherein the comprehensive generation value is calculated by the control target function, and an infeasible label or an additional penalty term is applied to the candidate control variable that violates the constraint condition.

[0110] If the candidate control variable satisfies any hard constraint violation, it is marked as infeasible:

[0111] feasible label (1 feasible, 0 infeasible), ∧ logical and, and the rest of the symbols are defined as before.

[0112] From the candidate control variables that have not been marked as infeasible, select the group with the smallest comprehensive generation value as the control variable and output it to the electrostatic precipitator, so that the control variable matches the scene recognition result.

[0113] When the scene recognition result is a sleep silent scene, increase the noise penalty weight and reduce the fan speed setting value, while reducing the high voltage output setting value and maintaining the dust removal effect by increasing the pulse frequency and adjusting the duty cycle; when the scene recognition result is a cooking oil fume scene, increase the dust removal effect weight and increase the fan speed setting value, while increasing the high voltage output setting value.

[0114] S6, output the control variable to the electrostatic precipitator to adjust the working state of the electrostatic field, and repeat S1-S5 in the subsequent control period to update the control variable, realizing dynamic closed-loop control of indoor electrostatic dust removal; S6 includes: at the beginning of each control period, decompose the control variable into high voltage drive instructions and fan drive instructions, and output them to the high voltage power supply module and the fan module respectively; wherein the high voltage drive instruction is used to set the high voltage output voltage or high voltage output current, pulse frequency, duty cycle, rising slope and polarity switching strategy, and the fan drive instruction is used to set the fan speed.

[0115] Control variable to instruction mapping expression:

[0116]

[0117] high voltage drive instruction vector, fan drive instruction.

[0118] A soft start process is performed when updating the high voltage drive instruction, which includes gradually increasing the high voltage output set value within a preset time; when it is detected that the leakage current exceeds a preset leakage threshold or a discharge event represented by the discharge event information occurs, a protection strategy is triggered, which includes one or more of reducing the high voltage output set value, reducing the duty cycle, reducing the rising edge slope, switching the polarity switching strategy, and reducing the fan speed.

[0119] Let the target set value be , and the maximum climbing step be , then:

[0120] the set voltage output in the current cycle, the set voltage in the previous cycle, the maximum allowed increment per cycle, the smaller value operator. Gradually increase to avoid instantaneous overshoot and cause corona instability and discharge.

[0121] The leakage threshold is denoted as , and the protection triggering condition is:

[0122] whether to trigger protection, ∨ logical or, leakage threshold, discharge event flag.

[0123] Example of action after triggering (reduce field strength, pulse energy and air flow disturbance at the same time, quickly escape from the discharge boundary):

[0124] ←: assignment update; : load reduction factor.

[0125] In the control cycle, updated particulate matter parameters, environmental parameters and operating parameters are collected, and a dust removal effect evaluation quantity is calculated; wherein the dust removal effect evaluation quantity includes particulate matter concentration reduction rate and unit energy consumption dust removal amount, and the dust removal effect evaluation quantity is used to correct the candidate control quantity generation range or control target function weight of the next control cycle.

[0126] Particulate matter concentration reduction rate (taking PM2.5 as an example):

[0127] : PM2.5 reduction rate.

[0128] Unit energy consumption dust removal amount (comprehensive PM2.5+PM10):

[0129] Unit energy consumption dust removal amount (the larger the more power saving), epsilon prevents zero, the numerator is the comprehensive dust removal amount, and the denominator is the periodic energy consumption.

[0130] Weight adaptive correction example (if energy efficiency is low, increase energy consumption weight):

[0131] Amplitude limiting function, Weight adjustment step, Target energy efficiency reference value, Upper and lower limits of energy consumption weight.

[0132] Repeat the steps S1 to S5 in the subsequent control period; update the control quantity based on the latest fusion state quantity and scene recognition result to realize dynamic closed-loop control of indoor electrostatic dust removal.

[0133] Closed-loop iteration is represented as:

[0134] Control strategy mapping, Fusion update mapping, Fusion state, Feature vector, Scene recognition result.

[0135] When the control quantity changes in the adjacent control period exceed the preset change threshold, the control quantity is subjected to amplitude limiting / gradual change to suppress the sudden change of electrostatic field working state caused by scene switching or transient fluctuation.

[0136] For any control quantity component , for example , let the maximum change step be , then: .

[0137] is the current (after output / update) value of the jth control quantity component in the kth control period. The control quantity component can be any control component such as high voltage set value, pulse frequency, duty cycle, rising edge slope, polarity switching related parameter or fan speed, etc. Saturation limiting function, used to limit the change amount δ to the interval ; : original change amount; : maximum change amplitude vector allowed by each control component.

[0138] The original change amount Amplitude limiting is performed so that the control amount change of adjacent periods does not exceed , thereby achieving amplitude limiting / gradual change output of the control amount and suppressing control mutation caused by scene switching or transient fluctuation.

[0139] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A dynamic control method for electrostatic precipitators based on multi-source data fusion, characterized in that, include: S1. Acquire particulate matter parameters and environmental parameters of indoor air, and simultaneously acquire the operating parameters of the electrostatic precipitator; S2. Process the particulate matter parameters, environmental parameters, and operating parameters, and construct a set of feature quantities based on the processed data to characterize the indoor dust load state, environmental impact state, device dust accumulation state, and discharge risk state. S3. Perform multi-source data fusion on the set of features to obtain fused state quantities; wherein the fused state quantities include particle concentration state, environmental impact factor, device state factor, and discharge risk factor; S4. Based on the fused state variables, perform indoor scene recognition and output the scene recognition result; S5. Based on the fusion state quantity and the scene recognition result, calculate the control quantity of the electrostatic dust removal device according to the preset control criteria; S6. Output the control quantity to the electrostatic dust removal device to adjust the working state of the electrostatic field, and repeat S1 to S5 in subsequent control cycles to update the control quantity, thereby realizing dynamic closed-loop control of indoor electrostatic dust removal.

2. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 1, characterized in that, The particulate matter parameters include PM2.5 and PM10; the environmental parameters include temperature, humidity, oil fume concentration, volatile organic compound (VOC) concentration, noise intensity, and wind speed; the operating parameters include high voltage output voltage or high voltage output current, leakage current, and discharge event information.

3. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 1, characterized in that, Time-domain filtering is performed on the particulate matter parameters and the environmental parameters to obtain smooth data; noise reduction processing is performed on the leakage current signal in the operating parameters to obtain the baseline component and peak component of the leakage current. Based on the smoothed data, the baseline component of the leakage current, and the spike component, a set of feature quantities is constructed.

4. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 3, characterized in that, The set of features includes: Characteristic quantities used to characterize indoor dust load status: PM2.5 concentration, PM10 concentration, PM2.5 concentration change rate, PM10 concentration change rate, and particulate matter concentration fluctuation intensity; Characteristic quantities used to characterize the state of environmental impact: temperature, humidity, oil fume concentration, VOCs concentration, wind speed, and the rate of change of the above environmental parameters; Characteristic quantities used to characterize the dust accumulation state of the device: wind speed attenuation, fan load change, and leakage current baseline drift. Characteristic quantities used to characterize discharge risk states: leakage current spike amplitude, leakage current spike count, leakage current spike energy, and discharge event count.

5. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 4, characterized in that, S3 includes: The set of features is normalized, and corresponding confidence weights are generated based on the fluctuation intensity and saturation state of each feature. The fusion state is obtained based on the normalized feature values ​​and their confidence weights, where the fusion state is updated jointly by the fusion state value at the previous time step and the feature value at the current time step.

6. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 5, characterized in that, S4 includes: The particle concentration state, environmental impact factor, device state factor, and discharge risk factor in the fusion state quantity are constructed as a scene discrimination input vector. The confidence level of each scene is obtained based on the scene input vector; Based on the confidence level of each scenario, a scenario candidate set is selected: the scenario with the highest confidence level is selected as the scenario recognition result; when the maximum confidence level is lower than the preset confidence level threshold, the output is a mixed scenario, and the top two scenarios with the highest confidence level in the mixed scenario are recorded as concurrent scenario recognition results. A hold time and a switching hysteresis threshold are set for the scene recognition result. The current scene recognition result is maintained within the hold time, and the scene recognition result is updated only when the confidence of a new scene continuously exceeds the switching hysteresis threshold.

7. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 6, characterized in that, The rule-based discrimination model determines the scene candidate set based on the following conditions: When the noise intensity is lower than the preset noise threshold, the wind speed is lower than the preset wind speed threshold, and the rate of change of particle concentration is lower than the preset rate of change threshold, the sleep silent scene is added to the scene candidate set. When the concentration of cooking fumes and VOCs are both higher than the corresponding preset concentration thresholds, and the particle concentration shows an upward trend within a preset time, the cooking fume scene is added to the scene candidate set. When the proportion of PM10 relative to PM2.5 is higher than the preset proportion threshold, and the fluctuation intensity of the particulate concentration is higher than the preset fluctuation threshold, the clean dust scene will be added to the scene candidate set. When the particulate concentration fluctuates intermittently and the proportion of PM10 is higher than the preset proportion threshold, and the wind speed is in the preset low to medium wind speed range, the pet activity dust scene will be added to the scene candidate set. When the humidity is higher than the preset humidity threshold, and the discharge risk factor increases or the leakage current baseline drift corresponding to the device status factor is greater than the preset drift threshold, the high humidity environment scenario is added to the scenario candidate set.

8. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 7, characterized in that, S5 includes: A control objective function is constructed based on the fused state variables, and the objective weights and constraint thresholds are set according to the scene recognition results. Generate a set of candidate control variables within a preset control period; For each set of candidate control variables, the particle concentration change, power consumption, noise intensity and discharge risk change in the next control cycle are predicted based on the fused state variables, and the corresponding comprehensive cost value is calculated. The group with the lowest comprehensive cost value is selected from the candidate control quantities that have never been marked as infeasible and output to the electrostatic dust removal device so that the control quantity matches the scene recognition result.

9. The dynamic control method for electrostatic dust removal based on multi-source data fusion according to claim 8, characterized in that, S6 includes: At the beginning of each control cycle, the control quantity is decomposed into high-voltage drive command and fan drive command, and output to the high-voltage power supply module and the fan module respectively. When updating the high-voltage drive command, a soft-start process is performed, which includes progressively increasing the high-voltage output setpoint within a preset time. When a leakage current exceeding a preset leakage threshold or a discharge event characterized by a discharge event occurs, a protection strategy is triggered. The protection strategy includes one or more of the following: reducing the high-voltage output setpoint, reducing the duty cycle, reducing the rise edge slope, switching the polarity switching strategy, and reducing the fan speed. During the control cycle, updated particulate matter parameters, environmental parameters, and operating parameters are collected, and the dust removal effect evaluation quantity is calculated. In subsequent control cycles, steps S1 to S5 are repeated to update the control variables based on the latest fused state variables and scene recognition results, so as to achieve dynamic closed-loop control of indoor electrostatic dust removal. When the change in the control quantity in an adjacent control cycle exceeds a preset change threshold, the control quantity is subjected to amplitude limiting or gradual change processing to suppress sudden changes in the electrostatic field working state caused by scene switching or transient fluctuations.

Images